Title :
An approach to risk forecast of project bidding based on SLS-SVM
Author :
Feng, Li-jun ; Liu, Jing-hong
Author_Institution :
Coll. of Urban & Rural Constr., Agric. Univ. of Hebei, Baoding, China
Abstract :
Due to the uncertainty, there are all kinds of risks during project bidding. In order to analyze and control the risk of project bidding better, it is necessary to forecast the risk of project bidding, and then help the decision-maker to manage it effectly. For this reason, this paper has put forward the method of sparse least squares support vector machine(SLS-SVM) and used it to forecast the risk of project bidding. For the sparse least squares support vector machine the sparseness is imposed by pruning and one can find the sparse solutions during less time. The experiments result illustrated how a significant amount of support vectors can be reduced without loss of performance in the case of small and large overlap of the underlying distributions and misclassified data.
Keywords :
business data processing; least squares approximations; project management; risk management; support vector machines; misclassified data; project bidding risk forecast; sparse least squares support vector machine; Cybernetics; Kernel; Least squares methods; Machine learning; Machine learning algorithms; Quadratic programming; Risk analysis; Risk management; Support vector machine classification; Support vector machines; Forecast; Project Bidding; Risk; Sparse least squares support vector machine;
Conference_Titel :
Machine Learning and Cybernetics, 2009 International Conference on
Conference_Location :
Baoding
Print_ISBN :
978-1-4244-3702-3
Electronic_ISBN :
978-1-4244-3703-0
DOI :
10.1109/ICMLC.2009.5212461